DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency

TL;DR

DRust introduces a practical distributed shared memory system leveraging Rust's ownership model, significantly simplifying coherence and achieving high throughput and scalability compared to existing systems.

Contribution

The paper presents DistR, a Rust-based DSM system that exploits ownership semantics for simplified coherence, outperforming state-of-the-art DSM systems in throughput and scalability.

Findings

DistR outperforms GAM by up to 2.64x in throughput.

DistR outperforms Grappa by up to 29.16x in throughput.

DistR scales better with the number of servers.

Abstract

Despite being a powerful concept, distributed shared memory (DSM) has not been made practical due to the extensive synchronization needed between servers to implement memory coherence. This paper shows a practical DSM implementation based on the insight that the ownership model embedded in programming languages such as Rust automatically constrains the order of read and write, providing opportunities for significantly simplifying the coherence implementation if the ownership semantics can be exposed to and leveraged by the runtime. This paper discusses the design and implementation of DistR, a Rust-based DSM system that outperforms the two state-of-the-art DSM systems GAM and Grappa by up to 2.64x and 29.16x in throughput, and scales much better with the number of servers.